Transit ridership forecasting under land use perspective at station level: A case study of Shenzhen

Authors: Xiangfu Kong*, Peking University, Jiawen Yang, Peking University
Topics: Land Use, Qualitative Research, Applied Geography
Keywords: station ridership forecasting, traffic and land use, rail transit, nonlinear regression
Session Type: Paper
Day: 4/4/2019
Start / End Time: 1:10 PM / 2:50 PM
Room: 8216, Park Tower Suites, Marriott, Lobby Level
Presentation File: No File Uploaded


Two problems are considered in this article. First, how do the land development intensity and the land use type influence station ridership? Second, what are the relationships between the station accessibility and trip rates for different land types? To answer the questions, a two-step nonlinear regression model is established and the parameters are estimated by the Gauss-Newton method. Based on the previous studies and testing of the linear correlation, four variables including floor area of different land types, bus lines, centrality and walking distance to the station are included in the model. Taking smart card data of 94 subways in Shenzhen as the cases, the results showed that: First, compared to the linear decay tendency, the decay rule is more in line with the exponential form; Second, trip rates of different land types ordering from large to small are: transport land > commercial land > official land ≈ urban village > industrial land > residential land > other land; Third, the impacts of walking distance on the trip rate ordering from large to small are: commercial land > official land > transport land > other land > residential land > urban village > industrial land. The estimation results confirm that the model has an accurate prediction on the station ridership. These findings can provide ridership prediction reference for rail transit and land use planning as well as analysis of residential trip characteristics.

Abstract Information

This abstract is already part of a session. View the session here.

To access contact information login